© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28423
    Prev
    Next
    INDEX
    Explanations

    expressions of humor and laughter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.18
    0.9%
    373
    +0.17
    0.8%
    267
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.18
    -0.00
    88
    +0.17
    0.02
    377
    +0.14
    0.02
    Negative Logits
     sovere
    -0.84
     glim
    -0.82
     laun
    -0.81
     redress
    -0.76
     Components
    -0.73
     bounds
    -0.70
     contracted
    -0.70
    natureconservancy
    -0.70
     thous
    -0.67
     fundament
    -0.67
    POSITIVE LOGITS
    cow
    1.30
    ita
    1.27
    cats
    1.21
    ol
    1.12
    ipop
    1.10
    olic
    0.89
    OL
    0.89
    cat
    0.85
    zers
    0.84
     Lol
    0.81
    Activations Density 0.126%

    No Known Activations